A Modelling of Stereo Matching Algorithm for Machine Vision Application

Stereo matching algorithm is a part of machine vision research area. The most challenging issue for stereo matching algorithm is to get an accurate corresponding point on the low texture region. Hence, this article proposes an algorithm utilizing the Sum of Absolute Differences (SAD), gradient matching and Bilateral Filter (BF) to increase the accuracy on this region. The combination of SAD with Red, Green and Blue (RGB) channels differences and gradient matching could improve the matching accuracy on the low texture region. Furthermore, the use of edge preserving filter such as BF that is capable to refine and remove the remaining noise on the final result. This filter is robust against high contrast and brightness. Based on the experimental analysis using standard benchmarking dataset from the Middlebury, the proposed work in this article achieves good accuracy on the low texture region. The comparison is also conducted with some established methods where the proposed framework performs much better.

[1]  Haidi Ibrahim,et al.  Improvement of stereo matching algorithm for 3D surface reconstruction , 2018, Signal Process. Image Commun..

[2]  Dongxiao Li,et al.  Fast stereo matching using adaptive guided filtering , 2014, Image Vis. Comput..

[3]  Agus Harjoko,et al.  Face Recognition Based on Symmetrical Half-Join Method using Stereo Vision Camera , 2016 .

[4]  Daphne Bavelier,et al.  Recovering stereo vision by squashing virtual bugs in a virtual reality environment , 2016, Philosophical Transactions of the Royal Society B: Biological Sciences.

[5]  Julian Eggert,et al.  Anisotropic Median Filtering for Stereo Disparity Map Refinement , 2018, VISAPP.

[6]  Rostam Affendi Hamzah,et al.  Disparity Mapping for Navigation of Stereo Vision Autonomous Guided Vehicle , 2009, 2009 International Conference of Soft Computing and Pattern Recognition.

[7]  Jonathan M. Garibaldi,et al.  Real-Time Correlation-Based Stereo Vision with Reduced Border Errors , 2002, International Journal of Computer Vision.

[8]  Andreas Geiger,et al.  Efficient Large-Scale Stereo Matching , 2010, ACCV.

[9]  Ikuko Shimizu,et al.  High accuracy local stereo matching using DoG scale map , 2017, 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA).

[10]  Liang-Gee Chen,et al.  Efficient Hardware Architecture for Large Disparity Range Stereo Matching Based on Belief Propagation , 2016, 2016 IEEE International Workshop on Signal Processing Systems (SiPS).

[11]  Yann LeCun,et al.  Computing the stereo matching cost with a convolutional neural network , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Andreas Geiger,et al.  Object scene flow for autonomous vehicles , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  R. A. Hamzah,et al.  Visualization of image distortion on camera calibration for stereo vision application , 2012, 2012 IEEE International Conference on Control System, Computing and Engineering.

[14]  Xiang Li,et al.  Accurate Dense Stereo Matching Based on Image Segmentation Using an Adaptive Multi-Cost Approach , 2016, Symmetry.

[15]  Haidi Ibrahim,et al.  Stereo matching algorithm for 3D surface reconstruction based on triangulation principle , 2016, 2016 1st International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE).

[16]  Christian Theobalt,et al.  Dense Wide-Baseline Scene Flow from Two Handheld Video Cameras , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[17]  Jean-Charles Bricola,et al.  Morphological processing of stereoscopic image superimpositions for disparity map estimation , 2016 .

[18]  Eric Psota,et al.  Real-Time Stereo Matching on CUDA Using an Iterative Refinement Method for Adaptive Support-Weight Correspondences , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

[19]  Widodo Budiharto,et al.  Multiple Moving Obstacles Avoidance of Service Robot using Stereo Vision , 2011 .

[20]  Rostam Affendi Hamzah,et al.  Disparity Refinement Process Based On Ransac Plane Fitting For Machine Vision Applications , 2018 .

[21]  Haifeng Xi,et al.  Wide Baseline Matching Using Support Vector Regression , 2013 .

[22]  Qian Liang,et al.  Stereo matching algorithm based on ground control points using graph cut , 2014, 2014 7th International Congress on Image and Signal Processing.

[23]  Qingxiong Yang,et al.  A non-local cost aggregation method for stereo matching , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Carsten Rother,et al.  Fast Cost-Volume Filtering for Visual Correspondence and Beyond , 2013, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Rostam Affendi Hamzah,et al.  Depth evaluation in selected region of disparity mapping for navigation of stereo vision mobile robot , 2010, 2010 IEEE Symposium on Industrial Electronics and Applications (ISIEA).

[26]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.